Leveraging Offline Data in Linear Latent Bandits von Kausik, Chinmaya, Tan, Kevin, Tewari, Ambuj

Volltext bestellen

Double Descent and Overfitting under Noisy Inputs and Distribution Shift for Linear Denoisers von Kausik, Chinmaya, Srivastava, Kashvi, Sonthalia, Rishi

Volltext bestellen

Learning Mixtures of Markov Chains and MDPs von Kausik, Chinmaya, Tan, Kevin, Tewari, Ambuj

Volltext bestellen

A Theoretical Framework for Partially Observed Reward-States in RLHF von Kausik, Chinmaya, Mutti, Mirco, Pacchiano, Aldo, Tewari, Ambuj

Volltext bestellen

An algorithm to calculate generalized Seifert matrices von Friedl, Stefan, Kausik, Chinmaya, Quintanilha, José Pedro

Volltext bestellen

Double Descent and Overfitting under Noisy Inputs and Distribution Shift for Linear Denoisers von Chinmaya Kausik, Srivastava, Kashvi, Sonthalia, Rishi

Volltext

Offline Policy Evaluation and Optimization under Confounding von Kausik, Chinmaya, Lu, Yangyi, Tan, Kevin, Makar, Maggie, Wang, Yixin, Tewari, Ambuj

Volltext bestellen

A Theoretical Framework for Partially Observed Reward-States in RLHF von Chinmaya Kausik, Mutti, Mirco, Pacchiano, Aldo, Tewari, Ambuj

Volltext

Learning Mixtures of Markov Chains and MDPs von Chinmaya Kausik, Tan, Kevin, Tewari, Ambuj

Volltext

An algorithm to calculate generalized Seifert matrices von Friedl, Stefan, Chinmaya Kausik, José Pedro Quintanilha

Volltext

Offline Policy Evaluation and Optimization under Confounding von Chinmaya Kausik, Lu, Yangyi, Tan, Kevin, Makar, Maggie, Wang, Yixin, Tewari, Ambuj

Volltext